Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terminology related to machine learning and natural language processing concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allee
    -0.19
    è¯ij
    -0.15
     Pump
    -0.15
    dma
    -0.14
    licted
    -0.14
    amber
    -0.14
    Enumerable
    -0.14
    abit
    -0.14
     pump
    -0.14
    ter
    -0.14
    POSITIVE LOGITS
     accord
    0.17
    orse
    0.15
    etine
    0.14
    arella
    0.14
    MOOTH
    0.14
    .ib
    0.14
    ")));
    0.14
    оÑĢаз
    0.14
    ddb
    0.14
    aph
    0.14
    Act Density 0.052%

    No Known Activations